Take home Exercise 3

Show the code

pacman::p_load(jsonlite, tidygraph, ggraph, 
               visNetwork, graphlayouts, ggforce, 
               skimr, tidytext, tidyverse, ggplot2, skimr, tm)

Show the code

mc3_data <- fromJSON("data/MC3.json")

Show the code

mc3_edges <- as_tibble(mc3_data$links) %>% 
  distinct() %>%
  mutate(source = as.character(source),
         target = as.character(target),
         type = as.character(type)) %>%
  group_by(source, target, type) %>%
    summarise(weights = n()) %>%
  filter(source!=target) %>%
  ungroup()

###Check missing values

Show the code

colSums(is.na(mc3_edges))

 source  target    type weights 
      0       0       0       0 

Check dupes

Show the code

mc3_edges[duplicated(mc3_edges),]

# A tibble: 0 × 4
# ℹ 4 variables: source <chr>, target <chr>, type <chr>, weights <int>

Show the code

mc3_nodes <- as_tibble(mc3_data$nodes) %>%
  mutate(country = as.character(country),
         id = as.character(id),
         product_services = as.character(product_services),
         revenue_omu = as.numeric(as.character(revenue_omu)),
         type = as.character(type)) %>%
  select(id, country, type, revenue_omu, product_services)

Show the code

mc3_nodes

# A tibble: 27,622 × 5
   id                                 country type  revenue_omu product_services
   <chr>                              <chr>   <chr>       <dbl> <chr>           
 1 Jones LLC                          ZH      Comp…  310612303. Automobiles     
 2 Coleman, Hall and Lopez            ZH      Comp…  162734684. Passenger cars,…
 3 Aqua Advancements Sashimi SE Expr… Oceanus Comp…  115004667. Holding firm wh…
 4 Makumba Ltd. Liability Co          Utopor… Comp…   90986413. Car service, ca…
 5 Taylor, Taylor and Farrell         ZH      Comp…   81466667. Fully electric …
 6 Harmon, Edwards and Bates          ZH      Comp…   75070435. Discount superm…
 7 Punjab s Marine conservation       Riodel… Comp…   72167572. Beef, pork, chi…
 8 Assam   Limited Liability Company  Utopor… Comp…   72162317. Power and Gas s…
 9 Ianira Starfish Sagl Import        Rio Is… Comp…   68832979. Light commercia…
10 Moran, Lewis and Jimenez           ZH      Comp…   65592906. Automobiles, tr…
# ℹ 27,612 more rows

CHeck missing value

Show the code

colSums(is.na(mc3_nodes))

              id          country             type      revenue_omu 
               0                0                0            21515 
product_services 
               0 

21515 missing from revenue_omu column

Check Dupes

Show the code

mc3_nodes[duplicated(mc3_nodes),]

# A tibble: 2,595 × 5
   id                              country type    revenue_omu product_services
   <chr>                           <chr>   <chr>         <dbl> <chr>           
 1 Smith Ltd                       ZH      Company          NA Unknown         
 2 Williams LLC                    ZH      Company          NA Unknown         
 3 Garcia Inc                      ZH      Company          NA Unknown         
 4 Walker and Sons                 ZH      Company          NA Unknown         
 5 Walker and Sons                 ZH      Company          NA Unknown         
 6 Smith LLC                       ZH      Company          NA Unknown         
 7 Smith Ltd                       ZH      Company          NA Unknown         
 8 Romero Inc                      ZH      Company          NA Unknown         
 9 Niger River   Marine life       Oceanus Company          NA Unknown         
10 Coastal Crusaders AS Industrial Oceanus Company          NA Unknown         
# ℹ 2,585 more rows

There are 2595 dupe entries

remove dupliated rows.

Show the code

mc3_nodes_unique <- distinct(mc3_nodes)

mc3_nodes_unique

# A tibble: 25,027 × 5
   id                                 country type  revenue_omu product_services
   <chr>                              <chr>   <chr>       <dbl> <chr>           
 1 Jones LLC                          ZH      Comp…  310612303. Automobiles     
 2 Coleman, Hall and Lopez            ZH      Comp…  162734684. Passenger cars,…
 3 Aqua Advancements Sashimi SE Expr… Oceanus Comp…  115004667. Holding firm wh…
 4 Makumba Ltd. Liability Co          Utopor… Comp…   90986413. Car service, ca…
 5 Taylor, Taylor and Farrell         ZH      Comp…   81466667. Fully electric …
 6 Harmon, Edwards and Bates          ZH      Comp…   75070435. Discount superm…
 7 Punjab s Marine conservation       Riodel… Comp…   72167572. Beef, pork, chi…
 8 Assam   Limited Liability Company  Utopor… Comp…   72162317. Power and Gas s…
 9 Ianira Starfish Sagl Import        Rio Is… Comp…   68832979. Light commercia…
10 Moran, Lewis and Jimenez           ZH      Comp…   65592906. Automobiles, tr…
# ℹ 25,017 more rows

Show the code

top_products <- mc3_nodes_unique %>%
  count(product_services, sort = TRUE) %>%
  top_n(10)

# Rename the columns
top_products <- top_products %>%
  rename(Products = product_services, Occurrences = n)

# Print the table
print(top_products)

# A tibble: 10 × 2
   Products                                                          Occurrences
   <chr>                                                                   <int>
 1 character(0)                                                            16395
 2 Unknown                                                                  4614
 3 Fish and seafood products                                                  63
 4 Seafood products                                                           55
 5 Fish and fish products                                                     31
 6 Food products                                                              31
 7 Canning, processing and manufacturing of seafood and other aquat…          23
 8 Footwear                                                                   21
 9 Seafood                                                                    20
10 Grocery products                                                           19

::: {.cell}

```{.r .cell-code}
skim(mc3_edges)

Data summary

Name	mc3_edges
Number of rows	24036
Number of columns	4
_______________________
Column type frequency:
character	3
numeric	1
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
source	0	1	6	700	0	12856	0
target	0	1	6	28	0	21265	0
type	0	1	16	16	0	2	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
weights	0	1	1	0	1	1	1	1	1	▁▁▇▁▁

:::

Show the code

DT::datatable(mc3_edges)

Show the code

ggplot(data = mc3_edges,
       aes(x = type)) +
  geom_bar()

Show the code

id1 <- mc3_edges %>%
  select(source) %>%
  rename(id = source)
id2 <- mc3_edges %>%
  select(target) %>%
  rename(id = target)
mc3_nodes1 <- rbind(id1, id2) %>%
  distinct() %>%
  left_join(mc3_nodes,
            unmatched = "drop")

Show the code

mc3_graph <- tbl_graph(nodes = mc3_nodes1,
                       edges = mc3_edges,
                       directed = FALSE) %>%
  mutate(betweenness_centrality = centrality_betweenness(),
         closeness_centrality = centrality_closeness())

Show the code

mc3_graph %>%
  filter(betweenness_centrality >= 100000) %>%
ggraph(layout = "fr") +
  geom_edge_link(aes(alpha=0.5)) +
  geom_node_point(aes(
    linewidth = betweenness_centrality,
    colors = "lightblue",
    alpha = 0.5)) +
  scale_linewidth_continuous(range=c(1,10))+
  theme_graph() +
  theme(text = element_text(family = "sans"))

Show the code

skim(mc3_nodes1)

Data summary

Name	mc3_nodes1
Number of rows	37324
Number of columns	5
_______________________
Column type frequency:
character	4
numeric	1
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
id	0	1.00	6	700	0	34121	0
country	29241	0.22	2	14	0	78	0
type	29241	0.22	7	16	0	3	0
product_services	29241	0.22	4	1737	0	1844	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
revenue_omu	34139	0.09	939014	12435469	3652.23	8261.03	16966.67	48266.67	310612303	▇▁▁▁▁

Show the code

DT::datatable(mc3_nodes1)

Show the code

ggplot(data = mc3_nodes1,
       aes(x = type)) +
  geom_bar()

##Text Sensing with tidytext

Show the code

#mc3_nodes1 %>% 
 #   mutate(n_fish = str_count(product_services, "fish") 

Record those “Unknwon” or”Charactor(0)” to “NA”

Show the code

mc3_nodes1$product_services[mc3_nodes1$product_services == "Unknown"] <- NA
mc3_nodes1$product_services[mc3_nodes1$product_services == "character(0)"] <- NA

Show the code

mc3_nodes_filtered <- mc3_nodes1 %>% 
  mutate(n_fish = str_count(product_services, "fish")) %>%
  arrange(desc(n_fish))

Show the code

mc3_nodes_filtered

# A tibble: 37,324 × 6
   id                          country type  revenue_omu product_services n_fish
   <chr>                       <chr>   <chr>       <dbl> <chr>             <int>
 1 Gvardeysk Sextant ОАО Cargo Uziland Comp…      73027. Fish salads (It…     11
 2 Taylor LLC                  ZH      Comp…     138982. Fish (anchovy, …     11
 3 SeaSelect Foods Salt spray  Marebak Comp…      41902. European whole …      7
 4 Arunachal Pradesh s S.A. d… Marebak Comp…      60346. Offers a wide r…      6
 5 suō yú Ltd. Liability Co    Coralm… Comp…      31567. Offers a wide r…      6
 6 Estrella del Mar SE         Riodel… Comp…      12565. Whole fresh fis…      5
 7 Mar de la Vida S.p.A. Expr… Gavano… Comp…      97490. Fresh and froze…      5
 8 Moore LLC                   ZH      Comp…      61273. Fish and fish p…      5
 9 Banded tilapia Corporation… Solova… Comp…      17498. Specialises in …      4
10 Costa de la Felicidad Ltd   Puerto… Comp…         NA  Diverse range o…      4
# ℹ 37,314 more rows

Show the code

ggplot(data = mc3_nodes_filtered, aes(x = type, y = n_fish)) +
geom_bar(stat = "identity")

Tokenisation

Show the code

token_nodes <- mc3_nodes1 %>%
  unnest_tokens(word, 
                product_services,
                to_lower = TRUE,
    # Exclude punctuation from tokenisation result
                strip_punct = TRUE)

Visualize the words extracted.

Show the code

token_nodes %>%
  count(word, sort = TRUE) %>%
  top_n(15) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(x = word, y = n)) +
  geom_col() +
  xlab(NULL) +
  coord_flip() +
      labs(x = "Count",
      y = "Unique words",
      title = "Count of unique words found in product_services field")

Show the code

stopwords_removed <- token_nodes %>% 
  anti_join(stop_words)

Show the code

stopwords_removed %>%
  count(word, sort = TRUE) %>%
  top_n(15) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(x = word, y = n)) +
  geom_col() +
  xlab(NULL) +
  coord_flip() +
      labs(x = "Count",
      y = "Unique words",
      title = "Count of unique words found in product_services field")

remove the rows with stop words + “NA”

Show the code

stopwords_removed <- token_nodes %>% 
  anti_join(stop_words) %>%
  filter(!is.na(word)) 

Show the code

stopwords_removed %>%
  count(word, sort = TRUE) %>%
  top_n(15) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(x = word, y = n)) +
  geom_col() +
  xlab(NULL) +
  geom_text(aes(label = n), vjust = 0.5, hjust = -0.1, size = 2, color = "black")+
  coord_flip() +
      labs(x = "Count",
      y = "Unique words",
      title = "Count of Top 15 unique words found in product_services field")+
  theme_minimal() 

Show the code

length(unique(stopwords_removed$word))

[1] 5467

Show the code

skim(mc3_nodes)

Data summary

Name	mc3_nodes
Number of rows	27622
Number of columns	5
_______________________
Column type frequency:
character	4
numeric	1
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
id	0	1	6	64	0	22929	0
country	0	1	2	15	0	100	0
type	0	1	7	16	0	3	0
product_services	0	1	4	1737	0	3244	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
revenue_omu	21515	0.22	1822155	18184433	3652.23	7676.36	16210.68	48327.66	310612303	▇▁▁▁▁

Show the code

stopwords_removed_unique <- stopwords_removed %>% 
  filter(!is.na(word))

Show the code

length(unique(stopwords_removed_unique$word))

[1] 5467

Show the code

stopwords_removed_unique %>%
  count(word, sort = TRUE) %>%
  top_n(15) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(x = word, y = n)) +
  geom_col() +
  geom_text(aes(label = n), vjust = 0.5, hjust = -0.1, size = 2, color = "black")+
  xlab(NULL) +
  coord_flip() +
      labs(x = "Count",
      y = "Unique words",
      title = "Count of Top 15 unique words found in product_services field")+
  theme_minimal() 

Show the code

words_fishery <- c("fish", "seafood", "frozen", "food", "fresh", "salmon", "shrimp", "shellfish", "sea", "squid", "water", "seafoods", "foods", "marine", "shipment", "shipping", "pier", "carp", "cod", "herring", "lichen", "mackerel", "pollock", "shark", "tuna", "ocean", "oyster", "clam", "lobster", "crab", "crustaceans", "crustacean", "bass")

mc3_nodes_fishery <- mc3_nodes_unique %>%
  filter(str_detect(product_services, paste(words_fishery, collapse = "|", sep = "")) | is.na(product_services))

print(mc3_nodes_fishery)

# A tibble: 1,534 × 5
   id                                 country type  revenue_omu product_services
   <chr>                              <chr>   <chr>       <dbl> <chr>           
 1 Makumba Ltd. Liability Co          Utopor… Comp…   90986413. Car service, ca…
 2 Harmon, Edwards and Bates          ZH      Comp…   75070435. Discount superm…
 3 Punjab s Marine conservation       Riodel… Comp…   72167572. Beef, pork, chi…
 4 Fisher Group                       ZH      Comp…   29981457. Steel (marketin…
 5 Morales, Young and Taylor          ZH      Comp…   23739782. Processed foods…
 6 Morgan LLC                         ZH      Comp…   17939781. Animal feed, an…
 7 Neptune's Harvest LC Transport     Riodel… Comp…    8726579. Frozen whole an…
 8 Victoria Falls   Limited Liabilit… Rio Is… Comp…    8014806. Domestic and in…
 9 Caracola del Mar NV Family         Rio Is… Comp…    7085566. Canned, frozen …
10 The Sea Lion NV Marine biology     Oceanus Comp…    6264744. One- to five-da…
# ℹ 1,524 more rows

Match ID from Nodes to Source in Edge

Show the code

targets <- mc3_edges %>%
  filter(source %in% mc3_nodes_fishery$id) %>%
  select(target)

Filter mc_edges with the extracted targets

Show the code

mc3_edges_new <- mc3_edges %>%
  filter(target %in% targets$target)

Targets that are not selected from mc3_edges

Show the code

Non_targets <- mc3_edges %>%
  filter(!target %in% targets$target) %>%
  distinct(target, .keep_all = TRUE)

Remove non_targets from Node_fishery

Show the code

mc3_nodes_fishery_new <- mc3_nodes_fishery %>%
  filter(!mc3_nodes_fishery$id %in% Non_targets$source)

result: none of the non-targets are in Node_fishery

Show the code

# maximum length of source is whopping 213, meaning that lot of c(",) inputs.
skim(mc3_edges_new)

Data summary

Name	mc3_edges_new
Number of rows	3711
Number of columns	4
_______________________
Column type frequency:
character	3
numeric	1
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
source	0	1	7	213	0	1493	0
target	0	1	6	27	0	2887	0
type	0	1	16	16	0	2	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
weights	0	1	1	0	1	1	1	1	1	▁▁▇▁▁

Show the code

mc3_edges_new_filtered <- mc3_edges_new %>%
  filter(startsWith(source, "c("))

#step 2

mc3_edges_new_split <- mc3_edges_new_filtered %>%
  separate_rows(source, sep = ", ") %>%
  mutate(source = gsub('^c\\(|"|\\)$', '', source))

#remove rows with grouped

mc3_edges_new2 <- mc3_edges_new %>%
  anti_join(mc3_edges_new_filtered)
        
#Add rows in step #2

mc3_edges_new2 <- mc3_edges_new2 %>%
  bind_rows(mc3_edges_new, mc3_edges_new_split)

#group

mc3_edges_new_groupby <- mc3_edges_new2 %>%
  group_by(source, target, type) %>%
  summarize(weight = n()) %>%
  filter(weight >1) %>%
  ungroup()

Show the code

#The maximum length of source looks more reasonable now at 57, suggesting all the multiple values have been dropped. 
skim(mc3_edges_new_groupby)

Data summary

Name	mc3_edges_new_groupby
Number of rows	3703
Number of columns	4
_______________________
Column type frequency:
character	3
numeric	1
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
source	0	1	7	57	0	1485	0
target	0	1	6	27	0	2887	0
type	0	1	16	16	0	2	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
weight	0	1	2	0.09	2	2	2	2	5	▇▁▁▁▁

Show the code

class(mc3_edges_new_groupby)

[1] "tbl_df"     "tbl"        "data.frame"

Show the code

#link the latest edges to the nodes

source_missing <-setdiff(mc3_edges_new_groupby$source, mc3_nodes_fishery_new$id)

source_missing_df <- tibble(
  id = source_missing,
  country = rep(NA_character_, length(source_missing)),
  type = rep("Company", length(source_missing)),
  revenue = rep(NA_real_, length(source_missing)),
  product_services = rep(NA_character_, length(source_missing))
)

target_missing <- setdiff(mc3_edges_new_groupby$target, mc3_nodes_fishery_new$id)

target_missing_df <- tibble(
  id = target_missing,
  country = rep(NA_character_, length(target_missing)),
  type = rep("Company", length(target_missing)),
  revenue = rep(NA_real_, length(target_missing)),
  product_services = rep(NA_character_, length(target_missing))
)

Show the code

#keep only id values from Nodes df also present in the edges df

mc3_nodes_fishery_new_filtered <- mc3_nodes_fishery_new %>%
  filter(id %in% c(mc3_edges_new_groupby$source, mc3_edges_new_groupby$target))

Show the code

mc3_nodes_fishery_new_df <- bind_rows(mc3_nodes_fishery_new_filtered, source_missing_df, target_missing_df)

Show the code

mc3_nodes_fishery_new_df <- mc3_nodes_fishery_new_df %>%
  mutate(revenue_omu = as.character(revenue_omu))

Show the code

mc3_nodes_fishery_grouped <- mc3_nodes_fishery_new_df %>%
  group_by(id) %>%
  summarize(
    count = n(),
    type_1 = ifelse(n() >= 1, type[1], NA),
    type_2 = ifelse(n() >= 2, type[2], NA),
    type_3 = ifelse(n() >= 3, type[3], NA),
    country = ifelse(n() == 1, country, paste(unique(country), collapse = ", ")),
    revenue_omu = ifelse(n() == 1, revenue_omu, paste(unique(revenue_omu), collapse = ", ")),
    product_services = ifelse(n() == 1, product_services, paste(unique(product_services), collapse = ", "))
  )

Show the code

top_products <- mc3_nodes_fishery_grouped %>%
  count(product_services, sort = TRUE) %>%
  top_n(10)

# Rename the columns
top_products <- top_products %>%
  rename(Products = product_services, Occurrences = n)

# Print the table
print(top_products)

# A tibble: 10 × 2
   Products                                                          Occurrences
   <chr>                                                                   <int>
 1 <NA>                                                                     3560
 2 Fish and seafood products                                                  37
 3 Seafood products                                                           23
 4 Canning, processing and manufacturing of seafood and other aquat…          18
 5 Fish and fish products                                                     15
 6 Seafood                                                                    11
 7 Fish and sea food products                                                  9
 8 Fish and seafoods products                                                  9
 9 Fresh and frozen seafood                                                    9
10 Tuna, sword fish, bass, trout, and salmon, as well as offers she…           9

Show the code

ids_fishing <- mc3_nodes_fishery_grouped %>%
  filter(str_detect(product_services, paste(words_fishery, collapse = "|", sep = "")) | is.na(product_services)) %>%
  pull(id)

Show the code

mc3_edges_fishery <- mc3_edges_new_groupby %>%
  filter(source %in% ids_fishing)

Show the code

mc3_nodes_fishery_ <- mc3_nodes_fishery_grouped %>%
  filter(id %in% c(mc3_edges_fishery$source, mc3_edges_fishery$target))

Show the code

mc3_fish_graph <- tbl_graph(nodes = mc3_nodes_fishery_,
                       edges = mc3_edges_fishery,
                       directed = FALSE) %>%
  mutate(betweenness_centrality = centrality_betweenness()) %>%
  ggraph(layout = "nicely") +
  scale_edge_width(range = c(0.01, 6)) +
  geom_node_point(aes(colour = type_1,
                      size = betweenness_centrality)) +
  theme_graph() +
  labs(size = "Betweenness Centrality")

mc3_fish_graph 

can see that most of the type is “Company”

Show the code

mc3_edges_fishery_in <- mc3_edges_fishery %>%
  rename(from = source, to = target)

mc3_nodes_fishery_in <- mc3_nodes_fishery_ %>%
  rename(group = type_1) 

# Create a visNetwork object with nodes and edges
visNetwork(nodes = mc3_nodes_fishery_in, edges = mc3_edges_fishery_in) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visOptions(highlightNearest = TRUE, nodesIdSelection = TRUE) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)

Find company personnal names () linked to multiple companies, that’s anomalies.

export csv files

Show the code

mc3_edges_fishery %>%
  group_by(target) %>%
  filter(n_distinct(source) > 1) %>%
  select(target) 

# A tibble: 1,324 × 1
# Groups:   target [508]
   target           
   <chr>            
 1 Elizabeth Jones  
 2 Michael Morrison 
 3 Amanda Robinson  
 4 Andrew Taylor    
 5 Brandon Cruz     
 6 Michael Thompson 
 7 Melissa Martin   
 8 Christopher Ramos
 9 Richard Smith    
10 Andrew Reed      
# ℹ 1,314 more rows

Show the code

mc3_edges_fishery %>%
  group_by(target) %>%
  summarise(count = n()) %>%
  arrange(desc(count)) %>%
  select(target, count)

# A tibble: 2,887 × 2
   target           count
   <chr>            <int>
 1 Michael Johnson     11
 2 John Smith          10
 3 Brian Smith          8
 4 Jennifer Johnson     8
 5 Michael Smith        8
 6 Richard Smith        8
 7 David Smith          7
 8 James Brown          7
 9 James Smith          7
10 Melissa Brown        7
# ℹ 2,877 more rows

Show the code

write.csv(mc3_edges_fishery, file='C:/Users/junso/Downloads/mc3_edges_fishery.csv')

Show the code

filtered_data <- mc3_edges_fishery %>%
  group_by(target) %>%
  summarise(count = n()) %>%
  arrange(desc(count)) %>%
  select(target, count)

filtered_data %>% 
  group_by(count) %>% 
  summarise(n = n()) %>% 
  mutate(percentage = round(n/sum(n) * 100, 2)) %>% 
  ggplot(aes(x = count, y = n, label = paste0(round(percentage, 2), "%"))) + 
  geom_bar(stat = "identity", fill = "lightblue", color = "black") + 
  xlab("Count") + 
  ylab("n") + 
  scale_x_continuous(breaks = unique(filtered_data$count)) + 
  geom_text(position = position_stack(vjust = 0.5))

Show the code

filtered_data2 <- mc3_edges_fishery %>%
  group_by(target) %>%
  summarise(count = n()) %>%
  filter(count > 1) %>%
  arrange(desc(count)) %>%
  select(target, count)

filtered_data2 %>%
  group_by(count) %>% 
  summarise(n = n()) %>% 
  mutate(percentage = round(n/sum(n) * 100, 2)) %>% 
  ggplot(aes(x = count, y = n, label = paste0(round(percentage, 2), "%"))) + 
  geom_bar(stat = "identity", fill = "lightblue", color = "black") + 
  xlab("Count") + 
  ylab("n") + 
  scale_x_continuous(breaks = unique(filtered_data$count)) + 
  geom_text(position = position_stack(vjust = 0.5))

Show the code

Michael_Johnson <- unique(mc3_edges_fishery_in$from[mc3_edges_fishery_in$to == "Michael Johnson"])

Michael_Johnson_edges <- subset(mc3_edges_fishery_in, from %in% Michael_Johnson)

Michael_Johnson_nodes <- subset(mc3_nodes_fishery_, id %in% c(Michael_Johnson_edges$from, Michael_Johnson_edges$to))

Show the code

# Create a visNetwork
visNetwork(nodes = Michael_Johnson_nodes, edges = Michael_Johnson_edges) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visOptions(highlightNearest = TRUE, nodesIdSelection = TRUE) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)

Show the code

top5 <- mc3_edges_fishery_in$from[mc3_edges_fishery_in$to %in% c("Michael Johnson", "John Smith", "Brian Smith", "Jennifer Johnson", "Michael Smith")]

Show the code

top5_edges <- subset(mc3_edges_fishery_in, from %in% top5)

top5_nodes <- subset(mc3_nodes_fishery_, id %in% c(top5_edges$from, top5_edges$to))

Show the code

# Create a visNetwork
visNetwork(nodes = top5_nodes, edges = top5_edges) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visOptions(highlightNearest = TRUE, nodesIdSelection = TRUE) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)

Conclusion

Through data exploration, I was able to observe a few anomalies.

1. individuals who have ownership in multiple companies. From analyzing three sub-network graphs, it was observed that these individuals tend to own a combination of large and small firms from various countries. While there is a possibility that everything is legitimate, it would be beneficial for FishEye to conduct a more thorough examination of these individuals who own companies across borders, particularly when they are the sole owners of smaller entities, as exemplified in the case of ‘James Brown’.

2. All of the id type is “Company”, surprisingly no beneficial owners and company contacts. Sort of expected looking from the distribution of types for Node dataframe intiially, but it might be noteworthy to investigate further what id type mean for illegal fishery.